© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86424
    Prev
    Next
    INDEX
    Explanations

    for followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ísimas
    -1.95
    aried
    -1.81
    ୪
    -1.77
    ⬈
    -1.76
    documented
    -1.73
    蕺
    -1.73
     inmedi
    -1.70
    came
    -1.70
    ſſen
    -1.70
     mesures
    -1.68
    POSITIVE LOGITS
    2
    1.95
     each
    1.79
     this
    1.72
    Samedi
    1.66
     Some
    1.65
    There
    1.63
     demikian
    1.61
     that
    1.58
     Numerous
    1.58
     sufficient
    1.55
    Activations Density 0.039%

    No Known Activations